Large Language Model Recall Uncertainty is Modulated by the Fan Effect
This paper evaluates whether large language models (LLMs) exhibit cognitive fan effects, similar to those discovered by Anderson in humans, after being pre-trained on human textual data. We conduct two sets of in-context recall experiments designed to elicit fan effects. Consistent with human results, we find that LLM recall uncertainty, measured via token probability, is influenced by the fan effect. Our results show that removing uncertainty disrupts the observed effect. The experiments suggest the fan effect is consistent whether the fan value is induced in-context or in the pre-training data. Finally, these findings provide in-silico evidence that fan effects and typicality are expressions of the same phenomena.
Code (1)
Tasks
Language ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
Confidence-Modulated Speculative Decoding for Large Language Models
Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static draftin…
Machine TranslationWhy Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented--enabling smaller st…
Knowledge DistillationLanguage ModelingLanguage ModellingHuman-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucination, the field has largely focused on measuring and improving calibratio…
Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) must learn dense masks from noisy, under-specified cues. We revisit the SegFormer decoder and show that three small, synergistic changes make weak supervision markedly more …
Semantic SegmentationUncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning
Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficient exploration. We propose Uncertainty-A…
Reinforcement Learning